aimnova.
DashboardMy LearningPaper MasteryStudy Plan

Aimnova site navigation

Stay in the loop

Get the latest study resources and updates

New features, study tips and exam insights — straight to your inbox.

IB Diploma

  • IB Past Papers
  • IB Study Notes
  • IB Question Bank
  • IB Mock Exams
  • IB Revision

IB Subjects

  • IB Math AA
  • IB Math AI
  • IB Economics
  • IB Business Management
  • IB Physics
  • IB Biology
  • View all IB subjects→

IB Past Papers

  • IB Math AA HL Past Papers
  • IB Math AA SL Past Papers
  • IB Math AI HL Past Papers
  • IB Math AI SL Past Papers
  • IB Economics HL Past Papers
  • IB Economics SL Past Papers
  • IB ESS Past Papers
  • View all past papers→

Study Resources

  • Study Notes
  • Question Bank
  • Mock Exams
  • Flashcards
  • Revision Guide
  • Exam Skills
  • Command Terms
  • Grade Calculator
  • Exam Timetable 2026

Aimnova

  • Features
  • Pricing
  • For Schools
  • For Parents
  • About Us
  • Blog
  • Contact
aimnova.

AI-powered study platform for smarter revision, past-paper analysis and examiner-style feedback.

TermsPrivacyCookies·© 2026 Aimnova. All rights reserved.8afc4e3

Aimnova is not affiliated with or endorsed by the International Baccalaureate Organization (IB).

NotesComputer ScienceTopic 4.1
Unit 4 · Machine learning · Topic 4.1

IB Computer Science — Machine learning fundamentals

Machine learning fundamentals

Exam technique guidePractice questions

Key concepts in Machine learning fundamentals

Key Idea: Machine learning finds patterns in data instead of following rules a programmer wrote. What a model can learn is decided entirely by the data it is given — which is why so many questions on this topic are really about the data.

Paper 1

  • Define the three types; identify which suits a scenario.

Paper 2

  • Extended ethical reasoning about a deployed system.

Both

  • Ethics marks come from consequences, not from naming a concern.

🧠 The three types

TypeLearns fromUse it when
SupervisedLabelled examplesThe correct answers already exist — spam, diagnosis
UnsupervisedUnlabelled dataThe groupings are what you are trying to discover
ReinforcementRewards for outcomesOnly the outcome can be scored — a game, a controller
Ask: do the correct answers already exist? If yes, supervised. If the groupings are the thing being discovered, unsupervised. If only the end result can be scored, reinforcement.

📊 Why accuracy misleads

Accuracy is one number, and it hides which predictions are wrong — which is usually what matters.

Important: On a condition affecting one person in a thousand, a model that answers 'no' every time is 99.9% accurate and has never identified a single case. The errors that matter are invisible in the single figure.

What to report instead

  • False positives and false negatives separately — they carry very different costs
  • Accuracy per group, not just overall, or a failure on a small group is hidden
  • For medical screening a false negative is far worse: the condition goes untreated

🖥️ Training against inference

TrainingInference
WorkThe whole dataset, repeatedlyOne input, one pass
Adjusts parameters?YesNo — they are fixed
TakesHours to weeksMilliseconds
NeedsMany acceleratorsSometimes just a phone
Training is dominated by matrix arithmetic, and every element can be computed independently — so thousands of simple cores beat a few powerful ones. But sequential, branch-heavy code gains nothing from parallel hardware.

📝 Exam-style questions

IB-style questionIdentify[3 marks]

A supermarket wants to group its customers by shopping habits, without deciding the groups in advance. Identify the type of machine learning required and justify your choice.

🔒 Model answer plan

See the mark-by-mark plan — for / against / judgement, with marking guidance — in study mode.

Claim your free topic →
IB-style questionDetermine[3 marks]

A screening model is tested on 4000 scans. It correctly identifies 76 of the 100 that show the condition, and correctly clears 3850 of the 3900 that do not. Determine its accuracy, and explain why that figure is misleading.

🔒 Model answer plan

See the mark-by-mark plan — for / against / judgement, with marking guidance — in study mode.

Claim your free topic →

✅ Quick check

Cover the answers.

Which type learns from rewards rather than answers? Reinforcement learning.

What is overfitting? Fitting the training data so closely — including its noise — that new data is handled badly. The model learned the examples, not the pattern.

Why keep test data separate from training data? A model can score well on data it memorised. Held-back data measures generalisation, which is what actually matters.

Why does a GPU suit training? Training is parallel matrix arithmetic, and a GPU has thousands of cores to do it at once.

Can a phone run a model it could not train? Yes — inference is one forward pass with fixed parameters, a tiny fraction of training's cost.


Exam tips

  • Ask whether labels exist — that decides supervised versus unsupervised immediately.
  • Never quote accuracy alone; say what a majority-class guesser would score.
  • False negatives and false positives carry different costs. Name which matters here.
  • Training adjusts parameters over the whole dataset; inference is one pass with them fixed.
  • Parallel hardware only helps parallel work — sequential code gains nothing from a GPU.
  • Overfitting is fixed by more varied data or a simpler model, not by training longer.

What you'll learn in Topic 4.1

  • 4.1.1 Types of machine learning
  • 4.1.2 Hardware for machine learning
Suggested study order: Read the notes for each sub-topic below → test yourself with flashcards → attempt practice questions → review exam technique.

Study resources — 4.1 Machine learning fundamentals

4.1.1

Types of machine learning

Notes
4.1.2

Hardware for machine learning

Notes

Ready to study Machine learning fundamentals?

Get expert practice questions with instant AI feedback, and a study planner tailored to your IB Computer Science exam date.

Start studying free

Topic 4.1 Machine learning fundamentals forms a core part of Unit 4: Machine learning in IB Computer Science. Mastering these concepts will strengthen your understanding of connected topics across the syllabus and prepare you for exam questions that require analysis, evaluation, and real-world application.

Previous topic
3.3 Database programming
Next topic
4.4 Ethical considerations
All Computer Science topics
Exam technique

Ready to practice?

Get AI-graded practice questions, mock exams, flashcards, and a personalised study plan — all aligned to your IB syllabus.

Start Studying Free

No credit card required · No time limit